Papers by Matthew Le

4 papers
Facebook AI’s WAT19 Myanmar-English Translation Task Submission (D19-52)

Copied to clipboard

Challenge: Using back-translation, we can improve generalization by using noisy channel re-ranking and ensembling.
Approach: They propose to use BPE-based transformer models to leverage monolingual data to improve generalization and use noisy channel re-ranking and ensembling to improve results.
Outcome: The proposed system improves on the baseline system trained exclusively on the provided small parallel dataset, and the human evaluation and BLEU score are higher.
Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings (P19-1)

Copied to clipboard

Challenge: Using hyperbolic embeddings, we can infer concept hierarchies from distributional contexts while also being able to predict missing “is-a”-relationships and correct wrong extractions.
Approach: They propose a method combining hyperbolic embeddings and Hearst patterns to set appropriate constraints for inferring “is-a” relationships from large text corpora and improve taxonomic consistency.
Outcome: The proposed method achieves state-of-the-art performance on a variety of hypernymy benchmarks.
The Source-Target Domain Mismatch Problem in Machine Translation (2021.eacl-main)

Copied to clipboard

Challenge: Despite the interconnected world we live in, people in different places talk about different things in different parts of the world.
Approach: They propose a metric to quantify the effect of local context in machine translation and propose measurable results.
Outcome: The proposed metric can be used to quantify the effect of local context on the use of language in machine translation systems on low resource languages.
Revisiting the Evaluation of Theory of Mind through Question Answering (D19-1)

Copied to clipboard

Challenge: Existing benchmarks for theory of mind are flawed due to dataset biases . evaluators have been using the Sally-Anne test to infer false beliefs in others .
Approach: They propose to use question answering to evaluate theory of mind . they propose to explicitly control for data regularities via a careful examination of the answer space .
Outcome: The proposed evaluation protocol and dataset control for data regularities via a careful examination of the answer space.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations